CNN中的各种操作

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
batch_size = 100
n_batch = mnist.train.num_examples

#初始化权值
def weight_variable(shape):
    inital = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(inital)


#初始化偏置
def bias_variable(shape):
    inital = tf.constant(0.1, shape=shape)
    return tf.Variable(inital)


#卷积层
def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

#池化层
def max_pool2x2(x):
    return tf.nn.max_pool(x, [1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')


x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])

#把输入向量转为4维向量,-1代表未知,如3*8 转为 -1 * 4 则行数应为6行
#转后表示 样例*宽*高*通道(黑白图片通道为1)
x_image = tf.reshape(x, [-1, 28, 28, 1])

#第一个卷积层,采样窗口5*5,卷积核有32个,从一个平面抽取
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

#应用卷积
#h_conv1 = tf.nn.relu(tf.matmul(x_image, W_conv1)+b_conv1) 传统神经网络
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1)+b_conv1)
h_pool1 = max_pool2x2(h_conv1)

#第二个卷积层,采样窗口5*5, 卷积核64个,从32个中抽取
W_conv2 = weight_variable(([5, 5, 32, 64]))
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2)+b_conv2)
h_pool2 = max_pool2x2(h_conv2)

##两次池化后变为7*7 即(14/2/2)*(14/2/2),要扁平化为(图向量)*案例, 一行代表一个case
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
keep_prob = tf.placeholder(tf.float32)

#全连接层,第一层把接受池化层的输出
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1))
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2)+b_fc2)

#交叉熵代价函数
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
#优化器adam
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

#对于onehot形式结果正确与否比较,得到一个bool型列表
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.nn.rnn_cell.BasicLSTMCell

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for epoch in range(21):
        for batch in range(n_batch):
            batch_xs, batch_ys=mnist.train.next_batch(batch_size)
            sess.run(train_step, {x:batch_xs, y:batch_ys, keep_prob:0.7})

        acc = sess.run(accuracy, {x:mnist.test.images, y:mnist.test.labels, keep_prob:0.7})
        print("Iter"+str(epoch)+",accuracy"+str(acc))

Leave A Comment